Large-scale population variant data is often used to filter and aid interpretation of variant calls in a single sample. These approaches do not incorporate population information directly into the process of variant calling, and are often limited to filtering which trades recall for precision. In this study, we develop population-aware DeepVariant models with a new channel encoding allele frequencies from the 1000 Genomes Project. This model reduces variant calling errors, improving both precision and recall in single samples, and reduces rare homozygous and pathogenic clinvar calls cohort-wide. We assess the use of population-specific or diverse reference panels, finding the greatest accuracy with diverse panels, suggesting that large, diverse panels are preferable to individual populations, even when the population matches sample ancestry. Finally, we show that this benefit generalizes to samples with different ancestry from the training data even when the ancestry is also excluded from the reference panel.

Machine learning (ML) systems often exhibit unexpectedly poor behavior when they are deployed in real-world domains. We identify underspecification in ML pipelines as a key reason for these failures. An ML pipeline is the full procedure followed to train and validate a predictor. Such a pipeline is underspecified when it can return many distinct predictors with equivalently strong test performance. Underspecification is common in modern ML pipelines that primarily validate predictors on held-out data that follow the same distribution as the training data. Predictors returned by underspecified pipelines are often treated as equivalent based on their training domain performance, but we show here that such predictors can behave very differently in deployment domains. This ambiguity can lead to instability and poor model behavior in practice, and is a distinct failure mode from previously identified issues arising from structural mismatch between training and deployment domains. We provide evidence that underspecfication has substantive implications for practical ML pipelines, using examples from computer vision, medical imaging, natural language processing, clinical risk prediction based on electronic health records, and medical genomics. Our results show the need to explicitly account for underspecification in modeling pipelines that are intended for real-world deployment in any domain.

Logistic regression remains one of the most widely used tools in applied statistics, machine learning and data science. However, in moderately high-dimensional problems, where the number of features $d$ is a non-negligible fraction of the sample size $n$, the logistic regression maximum likelihood estimator (MLE), and statistical procedures based the large-sample approximation of its distribution, behave poorly. Recently, Sur and Candès (2019) showed that these issues can be corrected by applying a new approximation of the MLE's sampling distribution in this high-dimensional regime. Unfortunately, these corrections are difficult to implement in practice, because they require an estimate of the \emph{signal strength}, which is a function of the underlying parameters $\beta$ of the logistic regression. To address this issue, we propose SLOE, a fast and straightforward approach to estimate the signal strength in logistic regression. The key insight of SLOE is that the Sur and Candès (2019) correction can be reparameterized in terms of the corrupted signal strength, which is only a function of the estimated parameters $\widehat \beta$. We propose an estimator for this quantity, prove that it is consistent in the relevant high-dimensional regime, and show that dimensionality correction using SLOE is accurate in finite samples. Compared to the existing ProbeFrontier heuristic, SLOE is conceptually simpler and orders of magnitude faster, making it suitable for routine use. We demonstrate the importance of routine dimensionality correction in the Heart Disease dataset from the UCI repository, and a genomics application using data from the UK Biobank.

MOTIVATION: Population-scale sequenced cohorts are foundational resources for genetic analyses, but processing raw reads into analysis-ready cohort-level variants remains challenging. RESULTS: We introduce an open-source cohort-calling method that uses the highly accurate caller DeepVariant and scalable merging tool GLnexus. Using callset quality metrics based on variant recall and precision in benchmark samples and Mendelian consistency in father-mother-child trios, we optimize the method across a range of cohort sizes, sequencing methods and sequencing depths. The resulting callsets show consistent quality improvements over those generated using existing best practices with reduced cost. We further evaluate our pipeline in the deeply sequenced 1000 Genomes Project (1KGP) samples and show superior callset quality metrics and imputation reference panel performance compared to an independently generated GATK Best Practices pipeline. AVAILABILITY AND IMPLEMENTATION: We publicly release the 1KGP individual-level variant calls and cohort callset (https://console.cloud.google.com/storage/browser/brain-genomics-public/research/cohort/1KGP) to foster additional development and evaluation of cohort merging methods as well as broad studies of genetic variation. Both DeepVariant (https://github.com/google/deepvariant) and GLnexus (https://github.com/dnanexus-rnd/GLnexus) are open-source, and the optimized GLnexus setup discovered in this study is also integrated into GLnexus public releases v1.2.2 and later. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

A rainbow graph is a graph that admits a vertex-coloring such that every color appears exactly once in the neighborhood of each vertex. We investigate some properties of rainbow graphs. In particular, we show that there is a bijection between the isomorphism classes of $n$-rainbow graphs on $2n$ vertices and the switching classes of graphs on $n$ vertices.